EP0617296A1 - Method and system for obstacle detection, installed on a automotive vehicle - Google Patents
Method and system for obstacle detection, installed on a automotive vehicle Download PDFInfo
- Publication number
- EP0617296A1 EP0617296A1 EP94400449A EP94400449A EP0617296A1 EP 0617296 A1 EP0617296 A1 EP 0617296A1 EP 94400449 A EP94400449 A EP 94400449A EP 94400449 A EP94400449 A EP 94400449A EP 0617296 A1 EP0617296 A1 EP 0617296A1
- Authority
- EP
- European Patent Office
- Prior art keywords
- plane
- vehicle
- sensor
- image
- matrix
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S11/00—Systems for determining distance or velocity not using reflection or reradiation
- G01S11/12—Systems for determining distance or velocity not using reflection or reradiation using electromagnetic waves other than radio waves
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
- G01S17/88—Lidar systems specially adapted for specific applications
- G01S17/93—Lidar systems specially adapted for specific applications for anti-collision purposes
- G01S17/931—Lidar systems specially adapted for specific applications for anti-collision purposes of land vehicles
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60R—VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR
- B60R21/00—Arrangements or fittings on vehicles for protecting or preventing injuries to occupants or pedestrians in case of accidents or other traffic risks
- B60R21/01—Electrical circuits for triggering passive safety arrangements, e.g. airbags, safety belt tighteners, in case of vehicle accidents or impending vehicle accidents
- B60R21/013—Electrical circuits for triggering passive safety arrangements, e.g. airbags, safety belt tighteners, in case of vehicle accidents or impending vehicle accidents including means for detecting collisions, impending collisions or roll-over
Definitions
- the present invention relates to a method and a device for detecting obstacles, on board a motor vehicle.
- Obstacle detection systems are known using image sensors or cameras, in particular of the CCD type (that is to say “Charge Coupled Device”, or in French: “Charge transfer device”).
- CCD Charge Coupled Device
- French Charge transfer device
- a camera makes it possible to obtain a two-dimensional image of the road scene, it does not directly give information concerning the depth, that is to say the distance from the obstacle to the point of view located in the vehicle.
- the object of the present invention is to provide an on-board obstacle detection system, in particular for a motor vehicle, which provides information on the distance from the obstacle to the vehicle while being precise and reliable.
- the method according to the invention is characterized in that it consists in detecting obstacles intersecting a plane P substantially parallel to the floor of the vehicle and passing through this vehicle, and in defining, in a reference linked to the plane P, the coordinates of each point of intersection of these obstacles with the plane P.
- the plane P can cut the vehicle, either in its upper part, for example at the interior mirror, and be slightly tilted down, or in its lower part, for example at the headlights and be slightly tilted up.
- the method according to the invention defines the coordinates O and z of each point of intersection of the obstacles with the plane P, the origin of the coordinates being located in the vehicle.
- the device for implementing the method, is characterized in that it comprises an image sensor consisting of at least one objective, a matrix sensor, for example CCD, on which an image is formed , and electronic image processing means coupled to information means for the driver of the vehicle, the objective consisting of a lens or a portion of cylindrical lens whose axis is parallel to the plane of the sensor matrix and inclined relative to the plane of symmetry of the vehicle, this image sensor being placed in the vehicle so that its field is superimposed on the plane P.
- an image sensor consisting of at least one objective
- a matrix sensor for example CCD
- electronic image processing means coupled to information means for the driver of the vehicle
- the objective consisting of a lens or a portion of cylindrical lens whose axis is parallel to the plane of the sensor matrix and inclined relative to the plane of symmetry of the vehicle, this image sensor being placed in the vehicle so that its field is superimposed on the plane P.
- the cylindrical lens is replaced by a superposition of lenses or portions of spherical lenses offset from one another so that their optical centers are on the same axis parallel to the plane of the matrix sensor but inclined relative to that -this.
- FIG. 1 This figure shows a vehicle 1 provided with an image sensor 2 according to the invention.
- the sensor 2 is fixed on the rear face of the interior rear-view mirror of the vehicle and is inclined slightly downwards.
- the field of this sensor can be assimilated, as will be explained below, to a plane P intersecting the obstacle constituted by a vehicle 3 placed in front of the vehicle 1.
- the sensor 2 which determines an origin O, covers in the plane P, an angle ⁇ likely to cover the entire width of the road.
- the plane P here intersects the vehicle 3 of FIG. 1, located on the same longitudinal axis as the vehicle 1, as well as a vehicle 4 located to the right of the vehicle A. More precisely, the plane P intersects the vehicles 3 and 4 along straight lines which, if these vehicles are at a certain distance from the vehicle 1, can be compared to their environment, A and B respectively.
- the device according to the invention makes it possible to determine the angle O and the dimension z of each point A and B in a reference frame linked to the plane P and originating from the half-line Oz formed by the intersection of the plane P with the plane of symmetry of the vehicle 1 .
- a source point S has been represented, which could be one of the points A or B in FIG. 2, a lens 5, a matrix sensor 6 and means 7 of electronic processing (for example digitization of the image then analysis of the digital image or direct electronic calculation) coupled to means 8 for informing the driver for assistance in driving the latter.
- These means 8 can be visual means, the information being displayed for example on a display screen integrated into the driving position and / or sound, such as an alarm or an artificial voice.
- the objective 5 consists of a superposition, in a plane parallel to that of the sensor 6, therefore substantially vertical, of parallelepipedic portions of spherical lenses 5a, 5b, ..., 5i, ... 5n offset from each other to the others so that their optical centers C a , ... C i , ..., C n are aligned on an axis parallel to the plane of the matrix sensor 6 and inclined relative to the plane of symmetry of the vehicle 1.
- the source point S has for image with respect to each of the lens portions 5a to 5n, an image point S a , S b , ... S i , ... S n .
- the optical centers C a to C n being aligned, the image points S a to S n are also aligned.
- the image on the sensor 6 of point S is a line segment.
- all the other source points, intersections of obstacles with the plane P have for image a straight line on the matrix sensor 6.
- the electronic means located in the housing interpret these images in order to determine the coordinates O and z of each source point. These coordinates are then brought to the knowledge of the driver, in various forms, by the means 8.
- the information concerning these coordinates can be supplemented or replaced by information concerning for example the presence or not obstacles, the distance of these obstacles to the vehicle, the relative speed of these obstacles with respect to the vehicle.
- FIG. 4 similar to FIG. 3 but on which the objective consists of a parallelepipedic portion of cylindrical lens 5 ′ whose axis is parallel to the plane of the matrix sensor 6 and is inclined relative to the plane of symmetry of the vehicle 1.
- This cylindrical lens is similar, from an optical point of view, to the superposition of portions of spherical lenses in FIG. 3. Indeed, if we assume the lenses of FIG. 3 sufficiently small, by a transition to the limit, these lenses are similar to a cylindrical lens.
- the axis of the cylindrical lens 5 ′ is analogous to the axis on which the optical centers C a to C n of the lens portions 5a to 5n are aligned.
- the two extreme optical centers of the lens 5 ' have been identified by C1 and C2.
- the image, on the sensor 6, of the source point S is, as in FIG. 3, a line segment whose ends are the two image points S'1 and S'2.
- FIG. 5 On a coordinate axis O'x, we have identified by i and j the abscissae relative to origins O ′, respectively O ′ ', of the ends of the line-image segment of the source point S, that is to say of the image points S1 and S2.
- Point O '' is defined below.
- the electronic means 7 include image processing algorithms (by way of nonlimiting example: contour extraction followed by a HOUGH transform) making it possible to extract from the different line segments, the line segment relative to each source point. For each line segment, we extract the equation of this segment and therefore the abscissas i and j of the points S1 and S2.
- the sensor 2 is shown diagrammatically in projection on a plane perpendicular to the planes of the matrix 6 and of the lens 5 ′.
- the projection in this plane of the matrix sensor 6 is the axis O'x and C'1 and C'2 are the projections of the optical centers C1 and C2.
- C'1 C'2 we have designated by a the distance C'1 C'2 and by d the distance between the lines C'1 C'2 and O'x, that is to say the distance between the lens and the matrix sensor. It was considered that point O in Figure 2 was confused with C'1.
- the invention makes it possible to locate all the obstacles intersecting the plane P; it applies particularly well to driving where the vertical dimension is not very significant and where a substantially horizontal dimension is sufficient, which allows the use of an optical system with horizontal convergence such as the lens described above . It gives precise and reliable results; moreover, it only uses an image sensor.
- the invention makes it possible to easily solve the problem of matching, that is to say of the pairing of the extreme image points (S a and S n or S1 and S2).
- the inter-sampling created by the superposition of lenses between the extreme lenses (5a and 5n) or by the inclined cylindrical lens makes it possible to connect these extreme image points by a line segment which it is easy to extract by means an image processing algorithm (by way of nonlimiting example: contour extraction followed by a HOUGH transform).
Abstract
Description
La présente invention se rapporte à un procédé et à un dispositif de détection d'obstacles, embarqué sur un véhicule automobile.The present invention relates to a method and a device for detecting obstacles, on board a motor vehicle.
On connaît des systèmes de détection d'obstacles utilisant des capteurs d'images ou caméras, notamment de type CCD (c'est-à-dire "Charge Coupled Device", ou en français : "Dispositif à transfert de charge"). Cependant, si une caméra permet d'obtenir une image en deux dimensions de la scène routière, elle ne donne pas directement de renseignement concernant la profondeur, c'est-à-dire la distance de l'obstacle au point de prise de vue situé dans le véhicule.Obstacle detection systems are known using image sensors or cameras, in particular of the CCD type (that is to say "Charge Coupled Device", or in French: "Charge transfer device"). However, if a camera makes it possible to obtain a two-dimensional image of the road scene, it does not directly give information concerning the depth, that is to say the distance from the obstacle to the point of view located in the vehicle.
Pour pallier cet inconvénient, on peut utiliser deux caméras et calculer la profondeur par un procédé de stéréo-vision, mais ce procédé est difficile à mettre en oeuvre. Outre le problème d'épipolarité se pose le problème de mise en correspondance, c'est-à-dire de l'appariement de chaque élément caractéristique de l'image de l'une des deux caméras avec l'élément correspondant de l'image de l'autre caméra. De plus, ce procédé demande, pour être robuste, des capacités de calcul très importantes et est donc mal adapté aux systèmes embarqués. Ces divers problèmes contribuent à un manque de précision et de fiabilité de ce procédé de stéréo-vision.To overcome this drawback, two cameras can be used and the depth can be calculated by a stereo-vision method, but this method is difficult to implement. In addition to the epipolarity problem, there is the problem of matching, that is to say the pairing of each characteristic element of the image of one of the two cameras with the corresponding element of the image. from the other camera. In addition, to be robust, this process requires very large computing capacities and is therefore ill-suited to on-board systems. These various problems contribute to a lack of precision and reliability of this stereo-vision process.
La présente invention a pour but un système de détection d'obstacles embarquable, notamment pour véhicule automobile, qui renseigne sur la distance de l'obstacle au véhicule tout en étant précis et fiable.The object of the present invention is to provide an on-board obstacle detection system, in particular for a motor vehicle, which provides information on the distance from the obstacle to the vehicle while being precise and reliable.
A cet effet, le procédé selon l'invention est caractérisé en ce qu'il consiste à détecter les obstacles coupant un plan P sensiblement parallèle au plancher du véhicule et passant par ce véhicule, et à définir, dans un repère lié au plan P, les coordonnées de chaque point d'intersection de ces obstacles avec le plan P.To this end, the method according to the invention is characterized in that it consists in detecting obstacles intersecting a plane P substantially parallel to the floor of the vehicle and passing through this vehicle, and in defining, in a reference linked to the plane P, the coordinates of each point of intersection of these obstacles with the plane P.
Le plan P peut couper le véhicule, soit dans sa partie supérieure, par exemple au niveau du rétroviseur intérieur, et être légèrement incliné vers le bas, soit dans sa partie inférieure, par exemple au niveau des projecteurs et être légèrement incliné vers le haut.The plane P can cut the vehicle, either in its upper part, for example at the interior mirror, and be slightly tilted down, or in its lower part, for example at the headlights and be slightly tilted up.
De préférence, le procédé selon l'invention définit les coordonnées O et z de chaque point d'intersection des obstacles avec le plan P, l'origine des coordonnées étant située dans le véhicule.Preferably, the method according to the invention defines the coordinates O and z of each point of intersection of the obstacles with the plane P, the origin of the coordinates being located in the vehicle.
Le dispositif selon l'invention, pour la mise en oeuvre du procédé, est caractérisé en ce qu'il comporte un capteur d'images constitué d'au moins un objectif, un capteur matriciel, par exemple CCD, sur lequel se forme une image, et des moyens de traitement électronique de l'image couplés à des moyens d'information du conducteur du véhicule, l'objectif étant constitué d'une lentille ou d'une portion de lentille cylindrique dont l'axe est parallèle au plan du capteur matriciel et incliné par rapport au plan de symétrie du véhicule, ce capteur d'images étant placé dans le véhicule de façon que son champ se superpose au plan P.The device according to the invention, for implementing the method, is characterized in that it comprises an image sensor consisting of at least one objective, a matrix sensor, for example CCD, on which an image is formed , and electronic image processing means coupled to information means for the driver of the vehicle, the objective consisting of a lens or a portion of cylindrical lens whose axis is parallel to the plane of the sensor matrix and inclined relative to the plane of symmetry of the vehicle, this image sensor being placed in the vehicle so that its field is superimposed on the plane P.
Selon une variante, la lentille cylindrique est remplacée par une superposition de lentilles ou de portions de lentilles sphériques décalées les unes par rapport aux autres de sorte que leurs centres optiques soient sur un même axe parallèle au plan du capteur matriciel mais incliné par rapport à celui-ci.According to a variant, the cylindrical lens is replaced by a superposition of lenses or portions of spherical lenses offset from one another so that their optical centers are on the same axis parallel to the plane of the matrix sensor but inclined relative to that -this.
Les coordonnées O, z et leurs barres d'incertitude sont déterminées par les relations suivantes :
où:
- δ est la résolution du capteur matriciel
- d est la distance entre l'objectif et le capteur matriciel
- a est la distance entre les projections, sur le plan P, des centres optiques extrèmes de l'objectif
- i est l'abscisse de l'intersection avec la première ligne de la matrice du capteur matriciel, du segment de droite qui constitue l'image du point dont les coordonnées sont recherchées, ce segment étant extrait au moyen d'un algorithme de traitement d'image.
- Δi=j-i, j étant l'abscisse de l'intersection avec la dernière ligne de la matrice du capteur matriciel, du segment de droite qui constitue l'image du point dont les coordonnées sont recherchées, ce segment étant extrait au moyen d'un algorithme de traitement d'image.
or:
- δ is the resolution of the matrix sensor
- d is the distance between the objective and the matrix sensor
- a is the distance between the projections, on the plane P, of the extreme optical centers of the objective
- i is the abscissa of the intersection with the first line of the matrix of the matrix sensor, of the line segment which constitutes the image of the point whose coordinates are sought, this segment being extracted by means of a processing algorithm d 'picture.
- Δi = ji, j being the abscissa of the intersection with the last line of the matrix of the matrix sensor, of the line segment which constitutes the image of the point whose coordinates are sought, this segment being extracted by means of a image processing algorithm.
L'invention va maintenant être décrite plus en détail, en référence à un mode de réalisation donné à titre d'exemple et représenté par les dessins annexés sur lesquels :
- la figure 1 est un schéma d'implantation du dispositif selon l'invention sur un véhicule,
- la figure 2 est un schéma de principe du dispositif selon l'invention,
- la figure 3 représente les éléments du dispositif selon l'invention,
- la figure 4 représente une variante de la figure 3,
- la figure 5 représente le capteur matriciel des figures 3 et 4,
- la figure 6 représente schématiquement en vue de dessus le dispositif optique des figures 3 et 4,
- la figure 7 représente, en vue agrandie, un détail de la figure 5.
- FIG. 1 is a layout diagram of the device according to the invention on a vehicle,
- FIG. 2 is a block diagram of the device according to the invention,
- FIG. 3 represents the elements of the device according to the invention,
- FIG. 4 represents a variant of FIG. 3,
- FIG. 5 represents the matrix sensor of FIGS. 3 and 4,
- FIG. 6 schematically represents a top view of the optical device of FIGS. 3 and 4,
- FIG. 7 represents, in an enlarged view, a detail of FIG. 5.
Sur toutes ces figures, les éléments correspondants portent les mêmes repères.In all these figures, the corresponding elements bear the same references.
On se reportera tout d'abord à la figure 1. Cette figure montre un véhicule 1 muni d'un capteur d'images 2 selon l'invention. Le capteur 2 est fixé sur la face arrière du rétroviseur intérieur du véhicule et est légèrement incliné vers le bas. Le champ de ce capteur peut être assimilé, comme on l'expliquera plus loin, à un plan P coupant l'obstacle que constitue un véhicule 3 placé devant le véhicule 1.Reference will firstly be made to FIG. 1. This figure shows a
Si l'on se reporte à la figure 2, on voit que le capteur 2, qui détermine une origine O, couvre dans le plan P, un angle γ susceptible de couvrir toute la largeur de la route. Le plan P coupe ici le véhicule 3 de la figure 1, situé sur le même axe longitudinal que le véhicule 1, ainsi qu'un véhicule 4 situé à droite du véhicule A.
Plus précisément, le plan P coupe les véhicules 3 et 4 selon des segments de droite que l'on peut, si ces véhicules sont à une certaine distance du véhicule 1, assimiler à leur milieu, respectivement A et B. Le dispositif selon l'invention permet de déterminer l'angle O et la cote z de chaque point A et B dans un repère lié au plan P et ayant pour origine la demi-droite Oz constituée par l'intersection du plan P avec le plan de symétrie du véhicule 1.If we refer to Figure 2, we see that the
More precisely, the plane P intersects the vehicles 3 and 4 along straight lines which, if these vehicles are at a certain distance from the
On se reportera maintenant à la figure 3 sur laquelle on a représenté un point source S, qui pourrait être l'un des points A ou B de la figure 2, un objectif 5, un capteur matriciel 6 et des moyens 7 de traitement électronique (par exemple numérisation de l'image puis analyse de l'image numérique ou calcul électronique direct) couplés à des moyens 8 d'information du conducteur pour l'aide à la conduite de celui-ci. Ces moyens 8 peuvent être des moyens visuels, les informations s'affichant par exemple sur un écran de visualisation intégré au poste de conduite et/ou sonores, tels qu'une alarme ou une voix artificielle.We will now refer to FIG. 3 in which a source point S has been represented, which could be one of the points A or B in FIG. 2, a
L'objectif 5 est constitué d'une superposition, dans un plan parallèle à celui du capteur 6, donc sensiblement vertical, de portions parallélépipèdiques de lentilles sphériques 5a, 5b,...,5i,...5n décalées les unes par rapport aux autres de sorte que leurs centres optiques C a,...Ci,...,Cn soient alignés sur un axe parallèle au plan du capteur matriciel 6 et incliné par rapport au plan de symétrie du véhicule 1. Sur la figure 3, on n'a représenté que 5 portions de lentilles mais on peut en superposer par exemple une vingtaine (n=20).The objective 5 consists of a superposition, in a plane parallel to that of the sensor 6, therefore substantially vertical, of parallelepipedic portions of
Le point source S a pour image par rapport à chacune des portions de lentilles 5a à 5n, un point-image Sa, Sb,...Si,...Sn. Les centres optiques Ca à Cn étant alignés, les points-images Sa à Sn le sont aussi. Ainsi, l'image sur le capteur 6 du point S est un segment de droite. De même, tous les autres points sources, intersections d'obstacles avec le plan P ont pour image un segment de droite sur le capteur matriciel 6. Les moyens électroniques situés dans le boîtier interprètent ces images afin de déterminer les coordonnées O et z de chaque point source. Ces coordonnées sont ensuite portées à la connaissance du conducteur, sous diverses formes, par les moyens 8. L'information concernant ces coordonnées peut être complétée ou remplacée par des informations concernant par exemple la présence ou non d'obstacles, la distance de ces obstacles au véhicule, la vitesse relative de ces obstacles par rapport au véhicule.The source point S has for image with respect to each of the
On se reportera maintenant à la figure 4, analogue à la figure 3 mais sur laquelle l'objectif est constitué d'une portion parallélépipédique de lentille cylindrique 5' dont l'axe est parallèle au plan du capteur matriciel 6 et est incliné par rapport au plan de symétrie du véhicule 1. Cette lentille cylindrique est analogue, du point de vue optique, à la superposition de portions de lentilles sphériques de la figure 3. En effet, si l'on suppose les lentilles de la figure 3 suffisamment petites, par un passage à la limite, ces lentilles sont assimilables à une lentille cylindrique. L'axe de la lentille cylindrique 5' est analogue à l'axe sur lequel sont alignés les centres optiques Ca à Cn des portions de lentilles 5a à 5n. On a repéré par C₁ et C₂ les deux centres optiques extrêmes de la lentille 5'. L'image, sur le capteur 6, du point source S est, comme sur la figure 3, un segment de droite dont les extrémités sont les deux points-images S'₁ et S'₂.We will now refer to FIG. 4, similar to FIG. 3 but on which the objective consists of a parallelepipedic portion of
Pour plus de simplicité, on considérera désormais que l'on se trouve dans le cas de la figure 4, la transposition du mode de la figure 4 à celui de la figure 3 se faisant aisément en remplaçant C₁ et C₂ par Ca et Cn et S₁ et S₂ par Sa et Sn.For simplicity, we will now consider that we are in the case of Figure 4, the transposition of the mode of Figure 4 to that of Figure 3 is easily done by replacing C₁ and C₂ by C a and C n and S₁ and S₂ by S a and S n .
On se reportera maintenant à la figure 5 sur laquelle on a représenté en détail le capteur matriciel 6. Sur un axe de coordonnées O'x, on a repéré par i et j les abscisses relatives par rapport à des origines O', respectivement O'', des extrémités du segment de droite-image du point source S, c'est-à-dire des points-images S₁ et S₂. Le point O'' est défini ci-après. Les moyens électroniques 7 comportent des algorithmes de traitement d'image (à titre d'exemple non limitatif : extraction de contour suivie d'une transformée de HOUGH) permettant d'extraire parmi les différents segments de droite, le segment de droite relatif à chaque point source. Pour chaque segment de droite, on extrait l'équation de ce segment et donc les abscisses i et j des points S₁ et S₂.We will now refer to FIG. 5 in which the matrix sensor 6 has been shown in detail. On a coordinate axis O'x, we have identified by i and j the abscissae relative to origins O ′, respectively O ′ ', of the ends of the line-image segment of the source point S, that is to say of the image points S₁ and S₂. Point O '' is defined below. The electronic means 7 include image processing algorithms (by way of nonlimiting example: contour extraction followed by a HOUGH transform) making it possible to extract from the different line segments, the line segment relative to each source point. For each line segment, we extract the equation of this segment and therefore the abscissas i and j of the points S₁ and S₂.
Sur la figure 6, on a représenté schématiquement le capteur 2 en projection sur un plan perpendiculaire aux plans de la matrice 6 et de la lentille 5'. La projection dans ce plan du capteur matriciel 6 est l'axe O'x et C'₁ et C'₂ sont les projections des centres optiques C₁ et C₂. On a désigné par a la distance C'₁ C'₂ et par d la distance entre les droites C'₁ C'₂ et O'x, c'est-à-dire la distance entre la lentille et le capteur matriciel. On a considéré que le point O de la figure 2 était confondu avec C'₁. On a désigné par δ la résolution du capteur matriciel 6, c'est-à-dire la distance inter-pixel. On a désigné par So la projection du point S sur l'axe Oz, par O'' la projection de C'₂ sur l'axe O'x, par O''z'' un axe parallèle à l'axe O'z et par S''o la projection de S sur cet axe O"z".In FIG. 6, the
On appelle λ et r les distances respectivement à l'axe O'z et O''z'' des projections sur l'axe O'x des impacts lumineux que constituent les points-images S₁ et S₂.We call λ and r the distances respectively to the axis O'z and O''z '' of the projections on the axis O'x of the light impacts that constitute the image points S₁ and S₂.
En regardant notamment la figure 7, on peut écrire :
avec
with
En considérant que l'impact lumineux a un diamètre d'1 pixel, on peut écrire :
d'où :
On voit d'autre part sur la figure 6 que :
donc :
On voit encore sur la figure 6, en considérant les triangles OSoS et OO'i
On voit de même, en considérant les triangles C'₂ S''oS et C'₂ O''j, que :
d'où
Or, on a vu que :
soit
Donc :
soit
Posons :
d'où
si l'on considère que C'₂ S''o est à peu près égal à zs on a :
Calculons zs min et zs max :
d'où :
En posant :
from where :
We see on the other hand in Figure 6 that:
so :
We still see in Figure 6, considering the triangles OS o S and OO'i
We also see, considering the triangles C'₂ S '' o S and C'₂ O''j, that:
from where
However, we have seen that:
is
So :
is
Let’s ask:
from where
if we consider that C'₂ S '' o is roughly equal to z s we have:
Let us calculate z s min and z s max:
from where :
By asking :
L'invention permet de localiser tous les obstacles coupant le plan P ; elle s'applique particulièrement bien à la conduite automobile où la dimension verticale n'est pas très significative et où une dimension sensiblement horizontale suffit, ce qui permet l'utilisation d'un système optique à convergence horizontale tel que la lentille décrite ci-dessus. Elle donne des résultats précis et fiables ; en outre, elle n'utilise qu'un capteur d'images.The invention makes it possible to locate all the obstacles intersecting the plane P; it applies particularly well to driving where the vertical dimension is not very significant and where a substantially horizontal dimension is sufficient, which allows the use of an optical system with horizontal convergence such as the lens described above . It gives precise and reliable results; moreover, it only uses an image sensor.
L'invention permet de résoudre aisément le problème de mise en correspondance, c'est-à-dire de l'appariement des points images extrêmes (Sa et Sn ou S₁ et S₂). En effet, l'interéchantillonnage créé par la superposition de lentilles entre les lentilles extrêmes (5a et 5n) ou par la lentille cylindrique inclinée, permet de relier ces points images extrêmes par un segment de droite qu'il est aisé d'extraire au moyen d'un algorithme de traitement d'image (à titre d'exemple non limitatif : extraction de contour suivie d'une transformée de HOUGH).The invention makes it possible to easily solve the problem of matching, that is to say of the pairing of the extreme image points (S a and S n or S₁ and S₂). Indeed, the inter-sampling created by the superposition of lenses between the extreme lenses (5a and 5n) or by the inclined cylindrical lens, makes it possible to connect these extreme image points by a line segment which it is easy to extract by means an image processing algorithm (by way of nonlimiting example: contour extraction followed by a HOUGH transform).
Claims (7)
caractérisé en ce qu'il comporte un capteur d'images constitué d'au moins un objectif, un capteur matriciel, par exemple CCD, sur lequel se forme une image, et des moyens de traitement électronique de l'image couplés à des moyens d'information du conducteur du véhicule, l'objectif étant constitué d'une lentille ou d'une portion de lentille cylindrique, dont l'axe est parallèle au plan du capteur matriciel et incliné par rapport au plan de symétrie du véhicule, ce capteur d'images étant placé dans le véhicule de façon que son champ se superpose au plan P 1- Obstacle detection device, in particular for a motor vehicle, intended to detect obstacles intersecting a plane P substantially parallel to the floor of the vehicle and passing through this vehicle and to define in a coordinate system linked to the plane P, the coordinates of each point intersection of these obstacles with the plane P,
characterized in that it comprises an image sensor made up of at least one objective, a matrix sensor, for example CCD, on which an image is formed, and electronic image processing means coupled to means of information for the driver of the vehicle, the objective consisting of a lens or a portion of cylindrical lens, the axis of which is parallel to the plane of the matrix sensor and inclined relative to the plane of symmetry of the vehicle, this sensor d being placed in the vehicle so that its field is superimposed on the plane P
caractérisé en ce que le capeur d'images est fixé sur la face arrière du rétroviseur intérieur du véhicule et est légèrement incliné vers le bas. 2- Device according to claim 1,
characterized in that the image sensor is fixed to the rear face of the interior rear view mirror of the vehicle and is tilted slightly downwards.
caractérisé en ce que le capteur d'images est fixé au véhicule au niveau des projecteurs et est légèrement incliné vers le haut. 3- Device according to claim 1,
characterized in that the image sensor is fixed to the vehicle at the level of the headlights and is tilted slightly upwards.
caractérisé en ce que la lentille cylindrique est remplacée par une superposition de lentilles ou de portions de lentilles sphériques décalées les unes par rapport aux autres de sorte que leurs centres optiques soient sur un même axe parallèle au plan du capteur matriciel mais incliné par rapport à celui-ci. 4- Device according to any one of the preceding claims,
characterized in that the cylindrical lens is replaced by a superposition of lenses or portions of spherical lenses offset from one another so that their optical centers are on the same axis parallel to the plane of the matrix sensor but inclined relative to that -this.
caractérisé en ce que les moyens de traitement électronique déterminent les coordonnées ϑ et z de chaque point d'intersection des obstacles avec le plan P, l'origine des coordonnées étant située au niveau du capteur, par les relations suivantes:
characterized in that the electronic processing means determine the coordinates ϑ and z of each point of intersection of the obstacles with the plane P, the origin of the coordinates being located at the level of the sensor, by the following relationships:
caractérisé en ce que les moyens d'information du conducteur sont visuels, et comportent par exemple un écran de visualisation intégré au poste de conduite. 6- Device according to any one of the preceding claims,
characterized in that the driver's information means are visual, and for example comprise a display screen integrated into the driving position.
caractérisé en ce que les moyens d'information du conducteur sont sonores. 7- Device according to any one of the preceding claims,
characterized in that the driver's information means are audible.
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
FR9303253A FR2703173B1 (en) | 1993-03-22 | 1993-03-22 | Method and device for obstacle detection, on board a motor vehicle. |
FR9303253 | 1993-03-22 |
Publications (2)
Publication Number | Publication Date |
---|---|
EP0617296A1 true EP0617296A1 (en) | 1994-09-28 |
EP0617296B1 EP0617296B1 (en) | 1998-04-22 |
Family
ID=9445197
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
EP94400449A Expired - Lifetime EP0617296B1 (en) | 1993-03-22 | 1994-03-03 | Method and system for obstacle detection, installed on a automotive vehicle |
Country Status (3)
Country | Link |
---|---|
EP (1) | EP0617296B1 (en) |
DE (1) | DE69409702T2 (en) |
FR (1) | FR2703173B1 (en) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP1343022A1 (en) * | 2002-03-08 | 2003-09-10 | Valeo Schalter und Sensoren GmbH | Procedure and system for detecting objects in the proximity of a vehicle |
CN103522970A (en) * | 2013-05-31 | 2014-01-22 | Tcl集团股份有限公司 | Vehicle driving safety detection method and system based on machine vision |
US9609289B2 (en) | 2004-04-15 | 2017-03-28 | Magna Electronics Inc. | Vision system for vehicle |
US9643605B2 (en) | 2002-05-03 | 2017-05-09 | Magna Electronics Inc. | Vision system for vehicle |
US10071676B2 (en) | 2006-08-11 | 2018-09-11 | Magna Electronics Inc. | Vision system for vehicle |
CN111699108A (en) * | 2017-12-14 | 2020-09-22 | 亮锐控股有限公司 | Luminaire for a vehicle headlamp with automatic beam mode selection |
Families Citing this family (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5877897A (en) | 1993-02-26 | 1999-03-02 | Donnelly Corporation | Automatic rearview mirror, vehicle lighting control and vehicle interior monitoring system using a photosensor array |
US6822563B2 (en) | 1997-09-22 | 2004-11-23 | Donnelly Corporation | Vehicle imaging system with accessory control |
US6891563B2 (en) | 1996-05-22 | 2005-05-10 | Donnelly Corporation | Vehicular vision system |
US7655894B2 (en) | 1996-03-25 | 2010-02-02 | Donnelly Corporation | Vehicular image sensing system |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
GB2139445A (en) * | 1983-05-06 | 1984-11-07 | Nissan Motor | Vehicle lidar |
FR2576126A1 (en) * | 1985-01-16 | 1986-07-18 | Reinaud Guy | Optical device for detection and protection of moving objects |
DE8717494U1 (en) * | 1987-09-15 | 1989-02-09 | Kolbatz, Klaus-Peter, 1000 Berlin, De | |
DE4114304C1 (en) * | 1991-05-02 | 1992-04-30 | Messerschmitt-Boelkow-Blohm Gmbh, 8012 Ottobrunn, De | Area surveillance camera - has detector surfaces separated from imaging areas and in form of parallel strips of optoelectronic devices |
EP0522520A1 (en) * | 1991-07-12 | 1993-01-13 | Bayerische Motoren Werke Aktiengesellschaft | Distance measuring apparatus for vehicules |
-
1993
- 1993-03-22 FR FR9303253A patent/FR2703173B1/en not_active Expired - Fee Related
-
1994
- 1994-03-03 DE DE69409702T patent/DE69409702T2/en not_active Expired - Fee Related
- 1994-03-03 EP EP94400449A patent/EP0617296B1/en not_active Expired - Lifetime
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
GB2139445A (en) * | 1983-05-06 | 1984-11-07 | Nissan Motor | Vehicle lidar |
FR2576126A1 (en) * | 1985-01-16 | 1986-07-18 | Reinaud Guy | Optical device for detection and protection of moving objects |
DE8717494U1 (en) * | 1987-09-15 | 1989-02-09 | Kolbatz, Klaus-Peter, 1000 Berlin, De | |
DE4114304C1 (en) * | 1991-05-02 | 1992-04-30 | Messerschmitt-Boelkow-Blohm Gmbh, 8012 Ottobrunn, De | Area surveillance camera - has detector surfaces separated from imaging areas and in form of parallel strips of optoelectronic devices |
EP0522520A1 (en) * | 1991-07-12 | 1993-01-13 | Bayerische Motoren Werke Aktiengesellschaft | Distance measuring apparatus for vehicules |
Non-Patent Citations (1)
Title |
---|
COWART ET AL.: "The Detection of Unresolved Targets Using the Hough Transform", COMPUTER VISION GRAPHICS AND IMAGE PROCESSING, vol. 21, no. 2, February 1983 (1983-02-01), DULUTH, MA US, pages 222 - 238 * |
Cited By (28)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP1343022A1 (en) * | 2002-03-08 | 2003-09-10 | Valeo Schalter und Sensoren GmbH | Procedure and system for detecting objects in the proximity of a vehicle |
US11203340B2 (en) | 2002-05-03 | 2021-12-21 | Magna Electronics Inc. | Vehicular vision system using side-viewing camera |
US10351135B2 (en) | 2002-05-03 | 2019-07-16 | Magna Electronics Inc. | Vehicular control system using cameras and radar sensor |
US10683008B2 (en) | 2002-05-03 | 2020-06-16 | Magna Electronics Inc. | Vehicular driving assist system using forward-viewing camera |
US9643605B2 (en) | 2002-05-03 | 2017-05-09 | Magna Electronics Inc. | Vision system for vehicle |
US10118618B2 (en) | 2002-05-03 | 2018-11-06 | Magna Electronics Inc. | Vehicular control system using cameras and radar sensor |
US9834216B2 (en) | 2002-05-03 | 2017-12-05 | Magna Electronics Inc. | Vehicular control system using cameras and radar sensor |
US10110860B1 (en) | 2004-04-15 | 2018-10-23 | Magna Electronics Inc. | Vehicular control system |
US10015452B1 (en) | 2004-04-15 | 2018-07-03 | Magna Electronics Inc. | Vehicular control system |
US9948904B2 (en) | 2004-04-15 | 2018-04-17 | Magna Electronics Inc. | Vision system for vehicle |
US10462426B2 (en) | 2004-04-15 | 2019-10-29 | Magna Electronics Inc. | Vehicular control system |
US9736435B2 (en) | 2004-04-15 | 2017-08-15 | Magna Electronics Inc. | Vision system for vehicle |
US10187615B1 (en) | 2004-04-15 | 2019-01-22 | Magna Electronics Inc. | Vehicular control system |
US9609289B2 (en) | 2004-04-15 | 2017-03-28 | Magna Electronics Inc. | Vision system for vehicle |
US11847836B2 (en) | 2004-04-15 | 2023-12-19 | Magna Electronics Inc. | Vehicular control system with road curvature determination |
US11503253B2 (en) | 2004-04-15 | 2022-11-15 | Magna Electronics Inc. | Vehicular control system with traffic lane detection |
US10306190B1 (en) | 2004-04-15 | 2019-05-28 | Magna Electronics Inc. | Vehicular control system |
US10735695B2 (en) | 2004-04-15 | 2020-08-04 | Magna Electronics Inc. | Vehicular control system with traffic lane detection |
US11951900B2 (en) | 2006-08-11 | 2024-04-09 | Magna Electronics Inc. | Vehicular forward viewing image capture system |
US10787116B2 (en) | 2006-08-11 | 2020-09-29 | Magna Electronics Inc. | Adaptive forward lighting system for vehicle comprising a control that adjusts the headlamp beam in response to processing of image data captured by a camera |
US11148583B2 (en) | 2006-08-11 | 2021-10-19 | Magna Electronics Inc. | Vehicular forward viewing image capture system |
US11396257B2 (en) | 2006-08-11 | 2022-07-26 | Magna Electronics Inc. | Vehicular forward viewing image capture system |
US11623559B2 (en) | 2006-08-11 | 2023-04-11 | Magna Electronics Inc. | Vehicular forward viewing image capture system |
US10071676B2 (en) | 2006-08-11 | 2018-09-11 | Magna Electronics Inc. | Vision system for vehicle |
CN103522970A (en) * | 2013-05-31 | 2014-01-22 | Tcl集团股份有限公司 | Vehicle driving safety detection method and system based on machine vision |
CN103522970B (en) * | 2013-05-31 | 2016-04-27 | 深圳Tcl工业研究院有限公司 | Based on vehicle driving safety method of inspection and the system of machine vision |
CN111699108A (en) * | 2017-12-14 | 2020-09-22 | 亮锐控股有限公司 | Luminaire for a vehicle headlamp with automatic beam mode selection |
CN111699108B (en) * | 2017-12-14 | 2023-07-25 | 亮锐控股有限公司 | Luminaire for a vehicle headlight with automatic beam mode selection |
Also Published As
Publication number | Publication date |
---|---|
EP0617296B1 (en) | 1998-04-22 |
FR2703173A1 (en) | 1994-09-30 |
FR2703173B1 (en) | 1995-04-28 |
DE69409702D1 (en) | 1998-05-28 |
DE69409702T2 (en) | 1998-11-12 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
EP1288072A2 (en) | Driver assistance device taking into account the overhang of other vehicles | |
EP0617296B1 (en) | Method and system for obstacle detection, installed on a automotive vehicle | |
EP1999484B1 (en) | Obstacle detection | |
WO1993021596A1 (en) | Road image sequence analysis device and method for obstacle detection | |
FR2752969A1 (en) | METHOD FOR DETECTING AN OBJECT FROM STEREOSCOPIC IMAGES | |
FR2899332A1 (en) | VISIBILITY FIELD MEASUREMENT DEVICE FOR VEHICLE AND DRIVING ASSISTANCE SYSTEM FOR VEHICLE | |
FR2864311A1 (en) | Display system for vehicle e.g. automobile, has extraction unit extracting position on image of scene from red light element of recognized object, and windshield having display zone in which display image is superposed on scene | |
EP1431918B1 (en) | Method and system for detecting road bends | |
EP2043044B1 (en) | Method and device for automobile parking assistance | |
WO2010133785A1 (en) | Method and device for extending a visibility area | |
FR2760554A1 (en) | METHOD FOR DETECTING RELIEF CONTOURS IN A PAIR OF STEREOSCOPIC IMAGES | |
EP0588815A1 (en) | Road image sequence analysis device and method for obstacle detection | |
FR3054673B1 (en) | MERGING DETECTION DATA AND FOLLOWING OBJECTS FOR MOTOR VEHICLE | |
FR3047105A1 (en) | METHOD AND DEVICE FOR DRIVING ASSISTANCE | |
FR3067999B1 (en) | METHOD FOR AIDING THE DRIVING OF A MOTOR VEHICLE | |
EP3629292A1 (en) | Reference point selection for extrinsic parameter calibration | |
FR3047589A1 (en) | METHOD AND DEVICE FOR ESTIMATING THE LATERAL POSITION OF A VEHICLE IN A CIRCULATION PATH | |
EP4148657A1 (en) | Method for generating a final image of the environment of a motor vehicle | |
EP3682320B1 (en) | Method for displaying the surroundings of a motor vehicle on a screen, and motor vehicle in which such a method is implemented | |
US10748303B2 (en) | Rear facing lane detection overlay | |
FR3056325A1 (en) | METHOD FOR DETERMINING AN ASSEMBLY DIMENSION OF A VEHICLE EQUIPPED WITH AN EXTERNAL LOAD | |
FR3087413A1 (en) | METHOD FOR DRIVING THE DISPLAY OF INFORMATION ON A SCREEN STRIP EQUIPPED WITH A BOAT GATEWAY | |
FR3052581B1 (en) | METHOD FOR MAKING A DEPTH CARD FROM SUCCESSIVE IMAGES OF A SINGLE CAMERA (MONO) EMBARKED IN A MOTOR VEHICLE | |
FR2893573A1 (en) | Frontal obstacle e.g. pedestrian crossing road, detecting method for motor vehicle, involves comparing reference image and image, projected by illuminator device and visualized by camera, to find non-deformed zones assimilated to obstacles | |
EP2193047B1 (en) | Assistance device for exiting a hidden lane |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PUAI | Public reference made under article 153(3) epc to a published international application that has entered the european phase |
Free format text: ORIGINAL CODE: 0009012 |
|
AK | Designated contracting states |
Kind code of ref document: A1 Designated state(s): DE GB IT |
|
17P | Request for examination filed |
Effective date: 19941010 |
|
17Q | First examination report despatched |
Effective date: 19961014 |
|
GRAG | Despatch of communication of intention to grant |
Free format text: ORIGINAL CODE: EPIDOS AGRA |
|
GRAG | Despatch of communication of intention to grant |
Free format text: ORIGINAL CODE: EPIDOS AGRA |
|
GRAH | Despatch of communication of intention to grant a patent |
Free format text: ORIGINAL CODE: EPIDOS IGRA |
|
GRAH | Despatch of communication of intention to grant a patent |
Free format text: ORIGINAL CODE: EPIDOS IGRA |
|
GRAA | (expected) grant |
Free format text: ORIGINAL CODE: 0009210 |
|
AK | Designated contracting states |
Kind code of ref document: B1 Designated state(s): DE GB IT |
|
GBT | Gb: translation of ep patent filed (gb section 77(6)(a)/1977) |
Effective date: 19980423 |
|
REF | Corresponds to: |
Ref document number: 69409702 Country of ref document: DE Date of ref document: 19980528 |
|
ITF | It: translation for a ep patent filed |
Owner name: JACOBACCI & PERANI S.P.A. |
|
PLBE | No opposition filed within time limit |
Free format text: ORIGINAL CODE: 0009261 |
|
STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: NO OPPOSITION FILED WITHIN TIME LIMIT |
|
26N | No opposition filed | ||
REG | Reference to a national code |
Ref country code: GB Ref legal event code: IF02 |
|
PGFP | Annual fee paid to national office [announced via postgrant information from national office to epo] |
Ref country code: IT Payment date: 20060331 Year of fee payment: 13 |
|
PGFP | Annual fee paid to national office [announced via postgrant information from national office to epo] |
Ref country code: GB Payment date: 20070226 Year of fee payment: 14 |
|
PGFP | Annual fee paid to national office [announced via postgrant information from national office to epo] |
Ref country code: DE Payment date: 20070307 Year of fee payment: 14 |
|
GBPC | Gb: european patent ceased through non-payment of renewal fee |
Effective date: 20080303 |
|
PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: DE Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES Effective date: 20081001 |
|
PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: GB Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES Effective date: 20080303 |
|
PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: IT Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES Effective date: 20070303 |